First training of PPO agent on Pyramids environment.

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f6b5593ad7fb701e9e8d73427cce4d9071aabf2e3fd844bf6998a6e247c875
+size 1417437

Pyramids/Pyramids-499948.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152eadcd2f7f21e8a3039ca9e7e24b5d70aac974d4c86c1e79c6f9383344511e
+size 1417437

Pyramids/Pyramids-499948.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753f79df88aff5dd639be2d99cdab47a0c1c7e3e2367059c2cf12607a6c664c7
+size 8651427

Pyramids/Pyramids-780922.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f6b5593ad7fb701e9e8d73427cce4d9071aabf2e3fd844bf6998a6e247c875
+size 1417437

Pyramids/Pyramids-780922.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdbb1beaacef82ccc7328edb200fd1ee6d2ea064c014d896c9d29280dbd3321
+size 8651427

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdbb1beaacef82ccc7328edb200fd1ee6d2ea064c014d896c9d29280dbd3321
+size 8651427

Pyramids/events.out.tfevents.1673944422.2694b56eafa7.23246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed92ba6bd0e027c5471a8c46112ef1ae9632a7ddb49f7749b77a4d6434f5e880
+size 260691

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-Pyramids
+      library_name: ml-agents
+---
+    
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
+  2. Step 1: Write your model_id: atorre/ppo-Pyramids
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,88 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    checkpoint_interval: 500000
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,76 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.2
+Multi-casting "[IP] 172.28.0.2 [Port] 55227 [Flags] 2 [Guid] 4117401756 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.127 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 1.312864 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 1 worker threads for Enlighten.
+PlayerConnection::CleanupXIO:  fatal IO error 11 (Resource temporarily unavailable) on X server ":0"
+      after 234 requests (234 known processed) with 0 events remaining.

run_logs/timers.json

@@ -0,0 +1,405 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.4624595046043396,
+            "min": 0.4624595046043396,
+            "max": 1.3868093490600586,
+            "count": 26
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 13947.7783203125,
+            "min": 13947.7783203125,
+            "max": 42070.25,
+            "count": 26
+        },
+        "Pyramids.Step.mean": {
+            "value": 779972.0,
+            "min": 29952.0,
+            "max": 779972.0,
+            "count": 26
+        },
+        "Pyramids.Step.sum": {
+            "value": 779972.0,
+            "min": 29952.0,
+            "max": 779972.0,
+            "count": 26
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.568676233291626,
+            "min": -0.14658166468143463,
+            "max": 0.568676233291626,
+            "count": 26
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 155.81729125976562,
+            "min": -34.73985290527344,
+            "max": 155.81729125976562,
+            "count": 26
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.015208727680146694,
+            "min": 0.0010243135038763285,
+            "max": 0.271362841129303,
+            "count": 26
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 4.167191505432129,
+            "min": 0.27144306898117065,
+            "max": 65.39844512939453,
+            "count": 26
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06873180995139086,
+            "min": 0.06573921082911381,
+            "max": 0.07225488690293141,
+            "count": 26
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0309771492708628,
+            "min": 0.4892529376180998,
+            "max": 1.060590602826172,
+            "count": 26
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.014059386240680595,
+            "min": 0.0009458740503079729,
+            "max": 0.015242839636768965,
+            "count": 26
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21089079361020893,
+            "min": 0.010317290585335015,
+            "max": 0.2133997549147655,
+            "count": 26
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.055377648209996e-05,
+            "min": 7.055377648209996e-05,
+            "max": 0.00029515063018788575,
+            "count": 26
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.0010583066472314995,
+            "min": 0.0010583066472314995,
+            "max": 0.0033750247749918,
+            "count": 26
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.12351789999999999,
+            "min": 0.12351789999999999,
+            "max": 0.19838354285714285,
+            "count": 26
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.8527684999999998,
+            "min": 1.3886848,
+            "max": 2.4432375,
+            "count": 26
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00235943821,
+            "min": 0.00235943821,
+            "max": 0.00983851593142857,
+            "count": 26
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.03539157315,
+            "min": 0.03539157315,
+            "max": 0.11251831918,
+            "count": 26
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011437034234404564,
+            "min": 0.011437034234404564,
+            "max": 0.39684292674064636,
+            "count": 26
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.1715555191040039,
+            "min": 0.1683458536863327,
+            "max": 2.777900457382202,
+            "count": 26
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 349.3448275862069,
+            "min": 332.43956043956047,
+            "max": 999.0,
+            "count": 26
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30393.0,
+            "min": 15984.0,
+            "max": 34041.0,
+            "count": 26
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.5613454385575922,
+            "min": -1.0000000521540642,
+            "max": 1.6216955381962987,
+            "count": 26
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 137.39839859306812,
+            "min": -30.676601640880108,
+            "max": 145.9525984376669,
+            "count": 26
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.5613454385575922,
+            "min": -1.0000000521540642,
+            "max": 1.6216955381962987,
+            "count": 26
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 137.39839859306812,
+            "min": -30.676601640880108,
+            "max": 145.9525984376669,
+            "count": 26
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.04159902990431874,
+            "min": 0.04159902990431874,
+            "max": 7.765137803740799,
+            "count": 26
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.660714631580049,
+            "min": 3.660714631580049,
+            "max": 124.24220485985279,
+            "count": 26
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 26
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 26
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1673944417",
+        "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1673946819"
+    },
+    "total": 2401.6863892289994,
+    "count": 1,
+    "self": 0.39779570499922556,
+    "children": {
+        "run_training.setup": {
+            "total": 0.14710872799969366,
+            "count": 1,
+            "self": 0.14710872799969366
+        },
+        "TrainerController.start_learning": {
+            "total": 2401.1414847960004,
+            "count": 1,
+            "self": 1.5874755200247819,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.51566898100009,
+                    "count": 1,
+                    "self": 4.51566898100009
+                },
+                "TrainerController.advance": {
+                    "total": 2394.855636035976,
+                    "count": 49824,
+                    "self": 1.853121960093631,
+                    "children": {
+                        "env_step": {
+                            "total": 1494.0950928778411,
+                            "count": 49824,
+                            "self": 1391.7245817680168,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 101.23936362989662,
+                                    "count": 49824,
+                                    "self": 4.87605545005772,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 96.3633081798389,
+                                            "count": 48876,
+                                            "self": 21.483079906790408,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 74.88022827304849,
+                                                    "count": 48876,
+                                                    "self": 74.88022827304849
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.1311474799276766,
+                                    "count": 49823,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2396.88050856301,
+                                            "count": 49823,
+                                            "is_parallel": true,
+                                            "self": 1122.0686625541803,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002752772999883746,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.001033865998579131,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0017189070013046148,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0017189070013046148
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0615624010006286,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005867099998795311,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005159009997441899,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005159009997441899
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0584847690006427,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0584847690006427
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001975021000362176,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004616490004991647,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015133719998630113,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015133719998630113
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1274.81184600883,
+                                                    "count": 49822,
+                                                    "is_parallel": true,
+                                                    "self": 31.720769021942942,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 18.896137503044883,
+                                                            "count": 49822,
+                                                            "is_parallel": true,
+                                                            "self": 18.896137503044883
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1117.4258751767757,
+                                                            "count": 49822,
+                                                            "is_parallel": true,
+                                                            "self": 1117.4258751767757
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 106.7690643070664,
+                                                            "count": 49822,
+                                                            "is_parallel": true,
+                                                            "self": 24.16646897301598,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 82.60259533405042,
+                                                                    "count": 398576,
+                                                                    "is_parallel": true,
+                                                                    "self": 82.60259533405042
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 898.9074211980414,
+                            "count": 49823,
+                            "self": 3.0712260500840785,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 154.13215791196671,
+                                    "count": 49823,
+                                    "self": 154.0119976509659,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.12016026100081945,
+                                            "count": 1,
+                                            "self": 0.12016026100081945
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 741.7040372359907,
+                                    "count": 345,
+                                    "self": 194.08276745405965,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 547.621269781931,
+                                            "count": 17811,
+                                            "self": 547.621269781931
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.81299947143998e-06,
+                    "count": 1,
+                    "self": 1.81299947143998e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.18270244599989383,
+                    "count": 1,
+                    "self": 0.002395254999100871,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.18030719100079295,
+                            "count": 1,
+                            "self": 0.18030719100079295
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,38 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499948,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499948.onnx",
+                "reward": 1.6249999776482582,
+                "creation_time": 1673945884.659464,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499948.pt"
+                ]
+            },
+            {
+                "steps": 780922,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-780922.onnx",
+                "reward": 1.6547499932348728,
+                "creation_time": 1673946819.2399633,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-780922.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 780922,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.6547499932348728,
+            "creation_time": 1673946819.2399633,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-780922.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}